feat: Phase 7I + UI refresh (capture form, memory/domain/activity pages, topnav)

Closes three gaps the user surfaced: (1) OpenClaw agents run blind
without AtoCore context, (2) mobile/desktop chats can't be captured
at all, (3) wiki UI hadn't kept up with backend capabilities.

Phase 7I — OpenClaw two-way bridge
- Plugin now calls /context/build on before_agent_start and prepends
  the context pack to event.prompt, so whatever LLM runs underneath
  (sonnet, opus, codex, local model) answers grounded in AtoCore
  knowledge. Captured prompt stays the user's original text; fail-open
  with a 5s timeout. Config-gated via injectContext flag.
- Plugin version 0.0.0 → 0.2.0; README rewritten.

UI refresh
- /wiki/capture — paste-to-ingest form for Claude Desktop / web / mobile
  / ChatGPT / other. Goes through normal /interactions pipeline with
  client="claude-desktop|claude-web|claude-mobile|chatgpt|other".
  Fixes the rotovap/mushroom-on-phone gap.
- /wiki/memories/{id} (Phase 7E) — full memory detail: content, status,
  confidence, refs, valid_until, domain_tags (clickable to domain
  pages), project link, source chunk, graduated-to-entity link, full
  audit trail, related-by-tag neighbors.
- /wiki/domains/{tag} (Phase 7F) — cross-project view: all active
  memories with the given tag grouped by project, sorted by count.
  Case-insensitive, whitespace-tolerant. Also surfaces graduated
  entities carrying the tag.
- /wiki/activity — autonomous-activity timeline feed. Summary chips
  by action (created/promoted/merged/superseded/decayed/canonicalized)
  and by actor (auto-dedup-tier1, auto-dedup-tier2, confidence-decay,
  phase10-auto-promote, transient-to-durable, tag-canon, human-triage).
  Answers "what has the brain been doing while I was away?"
- Home refresh: persistent topnav (Home · Activity · Capture · Triage
  · Dashboard), "What the brain is doing" snippet above project cards
  showing recent autonomous-actor counts, link to full activity.

Tests: +10 (capture page, memory detail + 404, domain cross-project +
empty + tag normalization, activity feed + groupings, home topnav,
superseded-source detail after merge). 440 → 450.

Known next: capture-browser extension for Claude.ai web (bigger
project, deferred); voice/mobile relay (adjacent).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

openclaw-plugins/atocore-capture/index.js

@@ -3,6 +3,11 @@ import { definePluginEntry } from "openclaw/plugin-sdk/core";
 const DEFAULT_BASE_URL = process.env.ATOCORE_BASE_URL || "http://dalidou:8100";
 const DEFAULT_MIN_PROMPT_LENGTH = 15;
 const DEFAULT_MAX_RESPONSE_LENGTH = 50_000;
+// Phase 7I — context injection: cap how much AtoCore context we stuff
+// back into the prompt. The /context/build endpoint respects a budget
+// parameter too, but we keep a client-side safety net.
+const DEFAULT_CONTEXT_CHAR_BUDGET = 4_000;
+const DEFAULT_INJECT_CONTEXT = true;
 
 function trimText(value) {
   return typeof value === "string" ? value.trim() : "";
@@ -41,6 +46,37 @@ async function postInteraction(baseUrl, payload, logger) {
   }
 }
 
+// Phase 7I — fetch a context pack for the incoming prompt so the agent
+// answers grounded in what AtoCore already knows. Fail-open: if the
+// request times out or errors, we just don't inject; the agent runs as
+// before. Never block the user's turn on AtoCore availability.
+async function fetchContextPack(baseUrl, prompt, project, charBudget, logger) {
+  try {
+    const res = await fetch(`${baseUrl.replace(/\/$/, "")}/context/build`, {
+      method: "POST",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify({
+        prompt,
+        project: project || "",
+        char_budget: charBudget
+      }),
+      signal: AbortSignal.timeout(5_000)
+    });
+    if (!res.ok) {
+      logger?.debug?.("atocore_context_fetch_failed", { status: res.status });
+      return null;
+    }
+    const data = await res.json();
+    const pack = trimText(data?.formatted_context || "");
+    return pack || null;
+  } catch (error) {
+    logger?.debug?.("atocore_context_fetch_error", {
+      error: error instanceof Error ? error.message : String(error)
+    });
+    return null;
+  }
+}
+
 export default definePluginEntry({
   register(api) {
     const logger = api.logger;
@@ -55,6 +91,28 @@ export default definePluginEntry({
         pendingBySession.delete(ctx.sessionId);
         return;
       }
+
+      // Phase 7I — inject AtoCore context into the agent's prompt so it
+      // answers grounded in what the brain already knows. Config-gated
+      // (injectContext: false disables). Fail-open.
+      const baseUrl = trimText(config.baseUrl) || DEFAULT_BASE_URL;
+      const injectContext = config.injectContext !== false && DEFAULT_INJECT_CONTEXT;
+      const charBudget = Number(config.contextCharBudget || DEFAULT_CONTEXT_CHAR_BUDGET);
+      if (injectContext && event && typeof event === "object") {
+        const pack = await fetchContextPack(baseUrl, prompt, "", charBudget, logger);
+        if (pack) {
+          // Prepend to the event's prompt so the agent sees grounded info
+          // before the user's question. OpenClaw's agent receives
+          // event.prompt as its primary input; modifying it here grounds
+          // whatever LLM the agent delegates to (sonnet, opus, codex,
+          // local model — doesn't matter).
+          event.prompt = `${pack}\n\n---\n\n${prompt}`;
+          logger?.debug?.("atocore_context_injected", { chars: pack.length });
+        }
+      }
+
+      // Record the ORIGINAL user prompt (not the injected version) so
+      // captured interactions stay clean for later extraction.
       pendingBySession.set(ctx.sessionId, {
         prompt,
         sessionId: ctx.sessionId,